On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929690605780992 |
|---|---|
| author | Madmon, Omer Pipano, Idan Reinman, Itamar Tennenholtz, Moshe |
| author_facet | Madmon, Omer Pipano, Idan Reinman, Itamar Tennenholtz, Moshe |
| contents | Publishers who publish their content on the web act strategically, in a behavior that can be modeled within the online learning framework. Regret, a central concept in machine learning, serves as a canonical measure for assessing the performance of learning agents within this framework. We prove that any proportional content ranking function with a concave activation function induces games in which no-regret learning dynamics converge. Moreover, for proportional ranking functions, we prove the equivalence of the concavity of the activation function, the social concavity of the induced games and the concavity of the induced games. We also study the empirical trade-offs between publishers' and users' welfare, under different choices of the activation function, using a state-of-the-art no-regret dynamics algorithm. Furthermore, we demonstrate how the choice of the ranking function and changes in the ecosystem structure affect these welfare measures, as well as the dynamics' convergence rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11517 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions Madmon, Omer Pipano, Idan Reinman, Itamar Tennenholtz, Moshe Computer Science and Game Theory Information Retrieval Publishers who publish their content on the web act strategically, in a behavior that can be modeled within the online learning framework. Regret, a central concept in machine learning, serves as a canonical measure for assessing the performance of learning agents within this framework. We prove that any proportional content ranking function with a concave activation function induces games in which no-regret learning dynamics converge. Moreover, for proportional ranking functions, we prove the equivalence of the concavity of the activation function, the social concavity of the induced games and the concavity of the induced games. We also study the empirical trade-offs between publishers' and users' welfare, under different choices of the activation function, using a state-of-the-art no-regret dynamics algorithm. Furthermore, we demonstrate how the choice of the ranking function and changes in the ecosystem structure affect these welfare measures, as well as the dynamics' convergence rate. |
| title | On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions |
| topic | Computer Science and Game Theory Information Retrieval |
| url | https://arxiv.org/abs/2405.11517 |